MA-RECON: Mask-aware deep-neural-network for robust fast MRI k-space interpolation

High-quality reconstruction of MRI images from under-sampled `k-space' data, which is in the Fourier domain, is crucial for shortening MRI acquisition times and ensuring superior temporal resolution. Over recent years, a wealth of deep neural network (DNN) methods have emerged, aiming to tackle...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-11
Hauptverfasser: Nitzan Avidan, Freiman, Moti
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Nitzan Avidan
Freiman, Moti
description High-quality reconstruction of MRI images from under-sampled `k-space' data, which is in the Fourier domain, is crucial for shortening MRI acquisition times and ensuring superior temporal resolution. Over recent years, a wealth of deep neural network (DNN) methods have emerged, aiming to tackle the complex, ill-posed inverse problem linked to this process. However, their instability against variations in the acquisition process and anatomical distribution exposes a deficiency in the generalization of relevant physical models within these DNN architectures. The goal of our work is to enhance the generalization capabilities of DNN methods for k-space interpolation by introducing `MA-RECON', an innovative mask-aware DNN architecture and associated training method. Unlike preceding approaches, our `MA-RECON' architecture encodes not only the observed data but also the under-sampling mask within the model structure. It implements a tailored training approach that leverages data generated with a variety of under-sampling masks to stimulate the model's generalization of the under-sampled MRI reconstruction problem. Therefore, effectively represents the associated inverse problem, akin to the classical compressed sensing approach. The benefits of our MA-RECON approach were affirmed through rigorous testing with the widely accessible fastMRI dataset. Compared to standard DNN methods and DNNs trained with under-sampling mask augmentation, our approach demonstrated superior generalization capabilities. This resulted in a considerable improvement in robustness against variations in both the acquisition process and anatomical distribution, especially in regions with pathology. In conclusion, our mask-aware strategy holds promise for enhancing the generalization capacity and robustness of DNN-based methodologies for MRI reconstruction from undersampled k-space data.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2709196567</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2709196567</sourcerecordid><originalsourceid>FETCH-proquest_journals_27091965673</originalsourceid><addsrcrecordid>eNqNir0KwjAYAIMgWLTvEHAOxMS21k1KRYcqFPcS9Sv0hyR-Sejr28EHcLkb7hYkElLu2GEvxIrEzvWcc5FmIklkROrqxOqyuN-OtFJuYGpSCPQNYJmGgGqc5SeDA20NUjTP4Dxt1YyqvtKBOateQDvtAa0Zle-M3pBlq0YH8c9rsj2Xj-LCLJpPAOeb3gTUc2pExvNdniZpJv-7vibuPqU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2709196567</pqid></control><display><type>article</type><title>MA-RECON: Mask-aware deep-neural-network for robust fast MRI k-space interpolation</title><source>Free E- Journals</source><creator>Nitzan Avidan ; Freiman, Moti</creator><creatorcontrib>Nitzan Avidan ; Freiman, Moti</creatorcontrib><description>High-quality reconstruction of MRI images from under-sampled `k-space' data, which is in the Fourier domain, is crucial for shortening MRI acquisition times and ensuring superior temporal resolution. Over recent years, a wealth of deep neural network (DNN) methods have emerged, aiming to tackle the complex, ill-posed inverse problem linked to this process. However, their instability against variations in the acquisition process and anatomical distribution exposes a deficiency in the generalization of relevant physical models within these DNN architectures. The goal of our work is to enhance the generalization capabilities of DNN methods for k-space interpolation by introducing `MA-RECON', an innovative mask-aware DNN architecture and associated training method. Unlike preceding approaches, our `MA-RECON' architecture encodes not only the observed data but also the under-sampling mask within the model structure. It implements a tailored training approach that leverages data generated with a variety of under-sampling masks to stimulate the model's generalization of the under-sampled MRI reconstruction problem. Therefore, effectively represents the associated inverse problem, akin to the classical compressed sensing approach. The benefits of our MA-RECON approach were affirmed through rigorous testing with the widely accessible fastMRI dataset. Compared to standard DNN methods and DNNs trained with under-sampling mask augmentation, our approach demonstrated superior generalization capabilities. This resulted in a considerable improvement in robustness against variations in both the acquisition process and anatomical distribution, especially in regions with pathology. In conclusion, our mask-aware strategy holds promise for enhancing the generalization capacity and robustness of DNN-based methodologies for MRI reconstruction from undersampled k-space data.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Experimentation ; Image reconstruction ; Inverse problems ; Magnetic resonance imaging ; Neural networks ; Training</subject><ispartof>arXiv.org, 2023-11</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Nitzan Avidan</creatorcontrib><creatorcontrib>Freiman, Moti</creatorcontrib><title>MA-RECON: Mask-aware deep-neural-network for robust fast MRI k-space interpolation</title><title>arXiv.org</title><description>High-quality reconstruction of MRI images from under-sampled `k-space' data, which is in the Fourier domain, is crucial for shortening MRI acquisition times and ensuring superior temporal resolution. Over recent years, a wealth of deep neural network (DNN) methods have emerged, aiming to tackle the complex, ill-posed inverse problem linked to this process. However, their instability against variations in the acquisition process and anatomical distribution exposes a deficiency in the generalization of relevant physical models within these DNN architectures. The goal of our work is to enhance the generalization capabilities of DNN methods for k-space interpolation by introducing `MA-RECON', an innovative mask-aware DNN architecture and associated training method. Unlike preceding approaches, our `MA-RECON' architecture encodes not only the observed data but also the under-sampling mask within the model structure. It implements a tailored training approach that leverages data generated with a variety of under-sampling masks to stimulate the model's generalization of the under-sampled MRI reconstruction problem. Therefore, effectively represents the associated inverse problem, akin to the classical compressed sensing approach. The benefits of our MA-RECON approach were affirmed through rigorous testing with the widely accessible fastMRI dataset. Compared to standard DNN methods and DNNs trained with under-sampling mask augmentation, our approach demonstrated superior generalization capabilities. This resulted in a considerable improvement in robustness against variations in both the acquisition process and anatomical distribution, especially in regions with pathology. In conclusion, our mask-aware strategy holds promise for enhancing the generalization capacity and robustness of DNN-based methodologies for MRI reconstruction from undersampled k-space data.</description><subject>Experimentation</subject><subject>Image reconstruction</subject><subject>Inverse problems</subject><subject>Magnetic resonance imaging</subject><subject>Neural networks</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNir0KwjAYAIMgWLTvEHAOxMS21k1KRYcqFPcS9Sv0hyR-Sejr28EHcLkb7hYkElLu2GEvxIrEzvWcc5FmIklkROrqxOqyuN-OtFJuYGpSCPQNYJmGgGqc5SeDA20NUjTP4Dxt1YyqvtKBOateQDvtAa0Zle-M3pBlq0YH8c9rsj2Xj-LCLJpPAOeb3gTUc2pExvNdniZpJv-7vibuPqU</recordid><startdate>20231126</startdate><enddate>20231126</enddate><creator>Nitzan Avidan</creator><creator>Freiman, Moti</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20231126</creationdate><title>MA-RECON: Mask-aware deep-neural-network for robust fast MRI k-space interpolation</title><author>Nitzan Avidan ; Freiman, Moti</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27091965673</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Experimentation</topic><topic>Image reconstruction</topic><topic>Inverse problems</topic><topic>Magnetic resonance imaging</topic><topic>Neural networks</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Nitzan Avidan</creatorcontrib><creatorcontrib>Freiman, Moti</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Nitzan Avidan</au><au>Freiman, Moti</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>MA-RECON: Mask-aware deep-neural-network for robust fast MRI k-space interpolation</atitle><jtitle>arXiv.org</jtitle><date>2023-11-26</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>High-quality reconstruction of MRI images from under-sampled `k-space' data, which is in the Fourier domain, is crucial for shortening MRI acquisition times and ensuring superior temporal resolution. Over recent years, a wealth of deep neural network (DNN) methods have emerged, aiming to tackle the complex, ill-posed inverse problem linked to this process. However, their instability against variations in the acquisition process and anatomical distribution exposes a deficiency in the generalization of relevant physical models within these DNN architectures. The goal of our work is to enhance the generalization capabilities of DNN methods for k-space interpolation by introducing `MA-RECON', an innovative mask-aware DNN architecture and associated training method. Unlike preceding approaches, our `MA-RECON' architecture encodes not only the observed data but also the under-sampling mask within the model structure. It implements a tailored training approach that leverages data generated with a variety of under-sampling masks to stimulate the model's generalization of the under-sampled MRI reconstruction problem. Therefore, effectively represents the associated inverse problem, akin to the classical compressed sensing approach. The benefits of our MA-RECON approach were affirmed through rigorous testing with the widely accessible fastMRI dataset. Compared to standard DNN methods and DNNs trained with under-sampling mask augmentation, our approach demonstrated superior generalization capabilities. This resulted in a considerable improvement in robustness against variations in both the acquisition process and anatomical distribution, especially in regions with pathology. In conclusion, our mask-aware strategy holds promise for enhancing the generalization capacity and robustness of DNN-based methodologies for MRI reconstruction from undersampled k-space data.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-11
issn 2331-8422
language eng
recordid cdi_proquest_journals_2709196567
source Free E- Journals
subjects Experimentation
Image reconstruction
Inverse problems
Magnetic resonance imaging
Neural networks
Training
title MA-RECON: Mask-aware deep-neural-network for robust fast MRI k-space interpolation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T13%3A46%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=MA-RECON:%20Mask-aware%20deep-neural-network%20for%20robust%20fast%20MRI%20k-space%20interpolation&rft.jtitle=arXiv.org&rft.au=Nitzan%20Avidan&rft.date=2023-11-26&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2709196567%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2709196567&rft_id=info:pmid/&rfr_iscdi=true